Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0801. Min Range: -6.0801
Max Act: 6.0801. Min Act: -0.1700
Data Index: 8180105 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0801. Min Range: -6.0801
Max Act: 6.0801. Min Act: -0.1700
Data Index: 790426 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.8926. Min Act: -0.1700
Data Index: 659524 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.8926. Min Act: -0.1700
Data Index: 6812924 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.8613. Min Act: -0.1700
Data Index: 249066 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.8301. Min Act: -0.1700
Data Index: 8258143 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.8301. Min Act: -0.1700
Data Index: 6521900 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.7676. Min Act: -0.1700
Data Index: 5939810 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.7363. Min Act: -0.1700
Data Index: 5859445 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.7363. Min Act: -0.1700
Data Index: 7815894 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.6738. Min Act: -0.1700
Data Index: 1578493 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.6426. Min Act: -0.1700
Data Index: 3537530 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.6738. Min Act: -0.1700
Data Index: 5418886 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.6113. Min Act: -0.1700
Data Index: 5031460 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.6113. Min Act: -0.1700
Data Index: 1966252 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.5801. Min Act: -0.1700
Data Index: 3863619 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.5801. Min Act: -0.1700
Data Index: 375392 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.5801. Min Act: -0.1700
Data Index: 7986814 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.5488. Min Act: -0.1700
Data Index: 3883380 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0801. Min Range: -6.0801
Max Act: 5.5801. Min Act: -0.1700
Data Index: 4172534 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19